[{"data":1,"prerenderedAt":380},["ShallowReactive",2],{"$fgukOamtKU1RtUiMFsqdObttmqPPQz0uc7bl_gj_LyX0":3,"$f-B1VXAGrDbLo2Tdd_iIUIQwMvyEP34m75Jz8TQjnM8w":245,"article-191":379},{"code":4,"msg":5,"data":6},0,"",{"category":7,"tag":11,"popular":19,"latest":86,"banner":126,"list":151,"cache":244},[8,9,10],"Agent","OpenAI","LLM",[8,12,13,14,9,10,15,16,17,18],"Google","Nvidia","Claude","DeepSeek","OCR","Chat","Generator",[20,29,37,45,54,62,70,79],{"id":21,"publish_date":22,"is_original":23,"collection":5,"cover_url":24,"cover_url_1_1":25,"title":26,"summary":27,"author":28},411,"2023-09-10",1,"article_res/cover/451ef50c225a8dc61c4336506794d13b.jpeg","article_res/cover/3ba9dc7a72f87d40b20fc2d225289ee3.jpeg","Idealism","Reality is created by the mind, we can change our reality by changing our mind. - Plato","Renee's Entrepreneurial Journey",{"id":30,"publish_date":31,"is_original":23,"collection":32,"cover_url":33,"cover_url_1_1":34,"title":35,"summary":36,"author":28},108,"2024-12-07","#LLM #AGI #AI Agent","article_res/cover/0039044422e4ec9f61c18e8ee1693bb0.jpeg","article_res/cover/4220971b108a91d21407d87bb02fbaa6.jpeg","Freysa.ai: The World's First Adversarial AI Agent Game","说服 Freysa 把钱包里的钱都拿出来",{"id":38,"publish_date":39,"is_original":23,"collection":40,"cover_url":41,"cover_url_1_1":42,"title":43,"summary":44,"author":28},12,"2025-03-09","#Oxford #Reasoning #LLM #Tool Use","article_res/cover/d448e9b3617a0b5302e1bd10c438bca9.jpeg","article_res/cover/864a468f9cc4c9317efadb3811909888.jpeg","Agentic Reasoning Framework - Significantly enhance the reasoning ability of LLMs through the integration of external tools using agents","Agentic Reasoning: Reasoning LLMs with Tools for Deep Research",{"id":46,"publish_date":47,"is_original":4,"collection":48,"cover_url":49,"cover_url_1_1":50,"title":51,"summary":52,"author":53},480,"2023-04-14","#Stable Diffusion","article_res/cover/0bdbe7cb1de4a78e54536e5d9afa7ec9.jpeg","article_res/cover/b3d6ffec0608dcfaf18c5a69906d1490.jpeg","【AIGC Learning】Generate Prompts Using Word Graphs - Stable Diffusion Web UI Series 13","AI will become a powerful tool in education, transforming the way we learn and deliver instruction.  \n- Reid Hoffman","--",{"id":55,"publish_date":56,"is_original":4,"collection":57,"cover_url":58,"cover_url_1_1":59,"title":60,"summary":61,"author":28},413,"2023-09-08","#Neuroscience","article_res/cover/74f8302d78a23d9430f22171eae136b6.jpeg","article_res/cover/87ca08af81bb304746be5261160964c0.jpeg","Can machines be conscious?","Do we have an ethical obligation to not turn off conscious machines? Would turning them off be murder? No. I don't lose any sleep over unplugging a conscious machine.\n- Jeff Hawkins, \"A Thousand Brains\"",{"id":63,"publish_date":64,"is_original":23,"collection":65,"cover_url":66,"cover_url_1_1":67,"title":68,"summary":69,"author":28},178,"2024-09-09","#Entrepreneurship","article_res/cover/a7224f025b55d1820408085faef63079.jpeg","article_res/cover/11a9995b096cbf64465ef01b8673b154.jpeg","37signals company","This damn sense of relaxation",{"id":71,"publish_date":72,"is_original":4,"collection":73,"cover_url":74,"cover_url_1_1":75,"title":76,"summary":77,"author":78},460,"2023-05-12","#Google","article_res/cover/b970687b12faa52da976f91248c2aa7b.jpeg","article_res/cover/d1e71b52cfd2c63bc6e71f3e85ff135c.jpeg","Learn what BRC-20 and Ordinals are using Google Bard","Ordinals - a new protocol that allows users to store arbitrary data on the Bitcoin blockchain","Google Bard mainly writes",{"id":80,"publish_date":81,"is_original":23,"collection":5,"cover_url":82,"cover_url_1_1":83,"title":84,"summary":85,"author":28},309,"2024-03-26","article_res/cover/9877f95894ee88532d0e6012c23a2df3.jpeg","article_res/cover/20092164ddc109ce6ae56b1984246751.jpeg","Learning the Cancun Upgrade with lepton and perplexity","Building a quick conversation-based search demo with Lepton AI.",[87,95,103,111,119],{"id":88,"publish_date":89,"is_original":23,"collection":90,"cover_url":91,"cover_url_1_1":92,"title":93,"summary":94,"author":28},627,"2025-03-20","#AI Avatar #AI Video Generation","article_res/cover/d95481358f73924989f8c4ee9c75d1c8.jpeg","article_res/cover/b74bc0fab01f8b6a6aa87696c0c3ed8b.jpeg","DisPose: Generating Animated Videos by Driving Video with Reference Images","DisPose is a controllable human image animation method that enhances video generation.",{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},626,"2025-03-21","#Deep Dive into LLMs #LLM #RL #Andrej Karpathy #AlphaGo","article_res/cover/446553a5c8f8f2f07d97b20eaee84e56.jpeg","article_res/cover/e6c2823409c9b34624064b9acbaca6f1.jpeg","AlphaGo and the Power of Reinforcement Learning - Andrej Karpathy's Deep Dive on LLMs (Part 9)","Simply learning from humans will never surpass human capabilities.",{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},625,"2025-03-22","#Deep Dive into LLMs #LLM #RL #RLHF #Andrej Karpathy","article_res/cover/8da81d38b1e5cf558a164710fd8a5389.jpeg","article_res/cover/96f028d76c362a99a0dd56389e8f7a9b.jpeg","Reinforcement Learning from Human Feedback (RLHF) - Andrej Karpathy's Deep Dive on LLMs (Part 10)","Fine-Tuning Language Models from Human Preferences",{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},624,"2025-03-23","#Deep Dive into LLMs #LLM #Andrej Karpathy #AI Agent #MMM","article_res/cover/a5e7c3d48bb09109684d6513287c661d.jpeg","article_res/cover/d3f22b7c0ab8d82fd2da457a299e0773.jpeg","The Future of Large Language Models - Andrej Karpathy's In-Depth Explanation of LLM (Part 11)","preview of things to come",{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},623,"#Google #Voe #AI Video Generation","article_res/cover/c44062fea0f336c2b96b3928292392c2.jpeg","article_res/cover/a041041c69092ad3db191c5bf3ff981b.jpeg","Trial of Google's video generation model VOE2","Our state-of-the-art video generation model",[127,135,143],{"id":128,"publish_date":129,"is_original":23,"collection":130,"cover_url":131,"cover_url_1_1":132,"title":133,"summary":134,"author":28},300,"2024-04-16","#AI in Science #AGI","article_res/cover/6bf01e793e0f33e848572412eebdf9b0.jpeg","article_res/cover/91a5ee21dafecb914fabeb9430d46ec1.jpeg","Would Einstein lose his job - AI and Quantum Computing: A Glimpse into the Near Future","So Einstein's job is still safe.",{"id":136,"publish_date":137,"is_original":23,"collection":138,"cover_url":139,"cover_url_1_1":140,"title":141,"summary":142,"author":28},101,"2024-12-14","#Nvidia #AI 3D Generator","article_res/cover/693e07c85980c5c0c8fde3f037733f23.jpeg","article_res/cover/9ea8edff2d5d303ff3fffff3f6f9c3d9.jpeg","NVIDIA's open-source 3D project LLaMA-Mesh","LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models",{"id":144,"publish_date":145,"is_original":23,"collection":146,"cover_url":147,"cover_url_1_1":148,"title":149,"summary":150,"author":28},131,"2024-11-10","#OpenAI","article_res/cover/87f8ed353ce39f31960e7cdfaf075a35.jpeg","article_res/cover/f597a63935f5cd32e484b4aadd6019e8.jpeg","ChatGPT has launched the Search function","Get fast, timely answers with links to relevant web sources.",{"big":152,"small":214},[153,181],{"title":154,"list":155},"AGENT",[156,157,165,173],{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":158,"publish_date":159,"is_original":23,"collection":160,"cover_url":161,"cover_url_1_1":162,"title":163,"summary":164,"author":28},622,"2025-03-24","#OWL #AI Agent #MAS #MCP #CUA","article_res/cover/cb50ca7f2bf4d1ed50202d7406e1c19a.jpeg","article_res/cover/4aa7aa3badfacf3cc84121334f1050dd.jpeg","OWL: Multi-agent collaboration","OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation",{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},620,"2025-03-26","#LLM #Google #Gemini #AI Agent","article_res/cover/53751a6dbbe990b1eb0b63f3b062aed4.jpeg","article_res/cover/031344981f0a212ff82d1f3a64aa5756.jpeg","Gemini 2.5 Pro, claimed to be far ahead of the competition, has been released with great fanfare: comprehensively surpassing other LLMs and topping the global rankings","Gemini 2.5: Our most intelligent AI model",{"id":174,"publish_date":175,"is_original":23,"collection":176,"cover_url":177,"cover_url_1_1":178,"title":179,"summary":180,"author":28},616,"2025-03-29","#MAS #AI Agent #AI Coder #MetaGPT #MGX","article_res/cover/9dcd702ad2035902e5e77967c34a1f1e.jpeg","article_res/cover/0a97fc4a922753c8f46ff38792020df8.jpeg","MGX - An automated website-building platform composed of multiple AI Agents","Your 24/7 AI Team | Dream, Chat, Create.",{"title":182,"list":183},"OPENAI",[184,191,199,206],{"id":185,"publish_date":167,"is_original":23,"collection":186,"cover_url":187,"cover_url_1_1":188,"title":189,"summary":190,"author":28},619,"#OpenAI #AI Image Generator #4o #MMM #AR Transformer","article_res/cover/2faffc97fcecf3151552cb0fd3206d89.jpeg","article_res/cover/1133cb4948af44cee2e7fbe79efb69e5.jpeg","The native image function of GPT-4o is officially launched","Introducing 4o Image Generation",{"id":192,"publish_date":193,"is_original":4,"collection":194,"cover_url":195,"cover_url_1_1":196,"title":197,"summary":198,"author":28},434,"2023-07-15","#Anthropic #OpenAI #Google #AI Code Generator #Claude","article_res/cover/e1b6f600a2b9f262a4392684e5f2ce25.jpeg","article_res/cover/6e1772e83f78f9a351ab23d3e414adee.jpeg","Latest Updates on Google Bard /Anthropic Claude2 / ChatGPT Code Interpreter","We want our models to use their programming skills to provide more natural interfaces to the basic functions of our computers.  \n - OpenAI",{"id":200,"publish_date":201,"is_original":4,"collection":146,"cover_url":202,"cover_url_1_1":203,"title":204,"summary":205,"author":28},417,"2023-08-24","article_res/cover/bccf897d50a88b18364e35f7466387e0.jpeg","article_res/cover/2f871085c1073717c1703ae86e18056f.jpeg","The GPT-3.5 Turbo fine-tuning (fine-tuning function) has been released～","Developers can now bring their own data to customize GPT-3.5 Turbo for their use cases.",{"id":207,"publish_date":208,"is_original":4,"collection":209,"cover_url":210,"cover_url_1_1":211,"title":212,"summary":213,"author":28},407,"2023-09-22","#OpenAI #AI Image Generator","article_res/cover/c59005e903d35cfc32346e2756e2728a.jpeg","article_res/cover/ba011d265e6d84b5c8cb6fd6b757b6cc.jpeg","Dall-E 3","DALL·E 3 understands significantly more nuance and detail, allowing you to easily translate your ideas into images.",[215,221,241],{"title":10,"list":216},[217,218,219,220],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":223},"GOOGLE",[224,225,226,234],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},615,"2025-03-30","#AI Researcher #AI Science #HKU #Google #AI Agent","article_res/cover/21fadf906067714bb0db31ae13a77c15.jpeg","article_res/cover/2697999a72bd26b22e85f0e92936d3ed.jpeg","AI-Researcher: LLM-driven全自动 scientific research assistant","AI-Researcher: Fully-Automated Scientific Discovery with LLM Agents  \nOpen-Sourced Alternative to Google AI Co-Scientist",{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},463,"2023-05-09","article_res/cover/89800f207723acdb55fc53bf999ebdc9.jpeg","article_res/cover/5764f369b4accd8f83e94aa4c077a175.jpeg","The Smallville sandbox world - A town with 25 virtual residents","Believable proxies of human behavior can empower interactive apps: Immersive environment, Rehearsal space, Prototyping tool",{"title":242,"list":243},"NVIDIA",[],true,{"code":4,"msg":5,"data":246},{"id":247,"publish_date":248,"is_original":23,"collection":249,"articles_id":250,"cover_url":251,"cover_url_1_1":252,"title":253,"summary":254,"author":28,"content":255,"popular":256,"list":321,"category":377,"tag":378},191,"2024-08-20","#AI Image Generator","BACatCWDn87QEQsOl9t1dg","article_res/cover/94dbec40d711e1cd21cdecf8b13a72fc.jpeg","article_res/cover/d6516e02d6b21aa2e61c5fce46fbfe98.jpeg","TurboEdit performs text-based image editing using a 3-4 step diffusion model.","TL;DR: We enable text-based image editing using 3-4 step diffusion models.","\u003Cdiv class=\"rich_media_content js_underline_content\n                       autoTypeSetting24psection\n            \" id=\"js_content\">\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>Today I came across an interesting project: TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models. My mom no longer has to worry about me not being able to afford Photoshop.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img js_insertlocalimg\" data-imgfileid=\"100006391\" data-ratio=\"0.39814814814814814\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802791170.320773237739036.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>The code is not yet open-sourced, but I've already experienced it using the Demo.\u003C/p>\u003Csection style='cursor: pointer;margin-top: 20px;margin-bottom: 20px;padding: 10px 20px;border-style: none;border-width: 3px;border-color: rgba(0, 0, 0, 0.4);border-radius: 0px;background: none 0% 0% / auto no-repeat scroll padding-box border-box rgb(250, 250, 250);width: auto;height: auto;box-shadow: rgba(0, 0, 0, 0) 0px 0px 0px 0px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Csection style=\"cursor: pointer;\">\u003Cp style=\"cursor: pointer;line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Original description:\u003C/p>\u003Cp style=\"cursor: pointer;line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Modified:\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006378\" data-ratio=\"0.5472222222222223\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802791490.14352236953754494.png\">\u003C/p>\u003C/section>\u003C/section>\u003Csection style='cursor: pointer;margin-top: 20px;margin-bottom: 20px;padding: 10px 20px;border-style: none;border-width: 3px;border-color: rgba(0, 0, 0, 0.4);border-radius: 0px;background: none 0% 0% / auto no-repeat scroll padding-box border-box rgb(250, 250, 250);width: auto;height: auto;box-shadow: rgba(0, 0, 0, 0) 0px 0px 0px 0px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Csection style=\"cursor: pointer;\">\u003Cp style=\"cursor: pointer;line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Original description:\u003C/p>\u003Cp style=\"cursor: pointer;line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Modified:\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006389\" data-ratio=\"0.5546296296296296\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802791310.5814906080159004.png\">\u003C/p>\u003C/section>\u003C/section>\u003Csection style='cursor: pointer;margin-top: 20px;margin-bottom: 20px;padding: 10px 20px;border-style: none;border-width: 3px;border-color: rgba(0, 0, 0, 0.4);border-radius: 0px;background: none 0% 0% / auto no-repeat scroll padding-box border-box rgb(250, 250, 250);width: auto;height: auto;box-shadow: rgba(0, 0, 0, 0) 0px 0px 0px 0px;color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;text-wrap: wrap;'>\u003Csection style=\"cursor: pointer;\">\u003Cp style=\"cursor: pointer;line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Original description:\u003C/p>\u003Cp style=\"cursor: pointer;line-height: 1.8em;letter-spacing: 0em;text-indent: 0em;padding-top: 8px;padding-bottom: 8px;\">Modified:\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006390\" data-ratio=\"0.5601851851851852\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802792920.1311334748625108.png\">\u003C/p>\u003C/section>\u003C/section>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);cursor: pointer;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">More effects\u003C/span>\u003C/h2>\u003Cp>\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100006384\" data-ratio=\"0.6537037037037037\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802793300.5367189106955046.png\">\u003C/p>\u003Cp>\u003Cimg class=\"rich_pages wxw-img\" data-imgfileid=\"100006383\" data-ratio=\"0.6694444444444444\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802809310.08169721693320486.png\">\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);cursor: pointer;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Technical details\u003C/span>\u003C/h2>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>TurboEdit uses a popular text-based editing framework —— the \"edit-friendly\" DDPM noise inversion method. They analyzed its application in fast sampling and attributed its failure to two aspects: the appearance of visual artifacts and insufficient editing strength. The research team attributed the artifact issue to mismatched noise statistics between the inverted noise and the expected noise schedule, proposing an adjusted noise schedule to correct this deviation. To enhance editing strength, they also proposed a pseudo-guidance method that effectively enhanced the editing effect without introducing new artifacts.\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cstrong>Solving the visual artifact problem\u003C/strong>\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>The research team observed that, following the \"edit-friendly\" method, the noise statistics of the inverted noise map deviated significantly from the expected values at each step. In multi-step diffusion models, these statistics tend to converge later in the diffusion process, allowing the model to handle any artifacts introduced during diffusion. However, in SDXL-Turbo, these steps are completely skipped, leaving the artifacts unresolved. The team found that these mismatched statistics roughly exhibited a time-shift phenomenon, with noise statistics approximately matching the expected values 200 steps earlier. Therefore, they eliminated this domain gap by providing a time-step parameter offset by 200 steps to the scheduler and model, successfully resolving the artifact issue.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006379\" data-ratio=\"0.6268518518518519\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802791250.011421826468666518.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>As shown in the figure, when using SDXL-Turbo, the easy-to-edit inversion leads to mismatched noise statistics (red) compared to the expected values (green). The research team proposed a simple time-offset method to realign these noise statistics (blue and purple), significantly reducing artifact generation.\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cstrong>Pseudo-guidance method\u003C/strong>\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>The research team analyzed the \"edit-friendly\" equation and proved that it could be decomposed into two parts —— one controlling the prompt intensity and the other transferring the original image to a new trajectory. The research team proposed applying CFG-like rescaling only to the prompt term, and the results showed that this method indeed enhances editing strength without introducing new artifacts. For more details, please refer to the paper.\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006382\" data-ratio=\"0.7518518518518519\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802810000.5857363887810174.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>As shown in the figure, when adjusting the cross-prompt term (wₚ, column) and the cross-trajectory term (wₜ, row), the study found that scaling only the cross-prompt term improves the editing effect without generating artifacts.\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cstrong>Equivalence of Edit-Friendly and Delta Denoising Score\u003C/strong>\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>The research team's study of the \"edit-friendly\" DDPM process revealed that its form is very similar to the correction method used in Delta Denoising Score. Surprisingly, the team proved that under appropriate learning rate selection and time-step sampling, these two methods are functionally equivalent and can generate identical results. This finding can also be extended to the recent Posterior Distillation Sampling (PDS) method, especially in its application to image editing.\u003C/p>\u003Ch2 style='margin-top: 30px;margin-bottom: 15px;color: rgba(0, 0, 0, 0.85);cursor: pointer;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;letter-spacing: normal;text-align: left;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cspan style=\"cursor: pointer;font-size: 22px;color: rgb(0, 0, 0);line-height: 1.5em;letter-spacing: 0em;font-weight: bold;display: block;\">Comparison\u003C/span>\u003C/h2>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cstrong>Comparison with existing multi-step methods\u003C/strong>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006385\" data-ratio=\"0.5962962962962963\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802794890.5486413410472555.png\">\u003Cspan style='background-color: rgb(255, 255, 255);color: rgb(0, 0, 0);font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;font-size: 16px;letter-spacing: normal;text-align: left;'>\u003C/span>\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>We compared our four-step editing results with the state-of-the-art editing methods under existing multi-step modes. Our method not only achieves comparable or superior image quality to the state-of-the-art methods but also has a significant speed advantage: it is six times faster than the fastest baseline method and even 630 times faster than the highest-scoring method.\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>\u003Cstrong>Comparison with existing few-step methods\u003C/strong>\u003C/p>\u003Cp style=\"text-align: center;\">\u003Cimg class=\"rich_pages wxw-img\" data-galleryid=\"\" data-imgfileid=\"100006386\" data-ratio=\"0.5416666666666666\" data-s=\"300,640\" data-type=\"png\" data-w=\"1080\" style=\"\" src=\"./assets/17423802797040.4606148530719103.png\">\u003C/p>\u003Cp style='margin-bottom: 0px;cursor: pointer;color: rgb(0, 0, 0);font-size: 16px;line-height: 1.8em;letter-spacing: normal;text-align: left;padding-top: 8px;padding-bottom: 8px;font-family: Optima, \"Microsoft YaHei\", PingFangSC-regular, serif;text-wrap: wrap;background-color: rgb(255, 255, 255);'>We further compared our method with other few-step editing methods. The results show that our method can better match the semantic intent of the edit while preserving the content of the original image. Additionally, our method successfully avoids the visual artifact issues present in the baseline \"edit-friendly\" method.\u003C/p>\u003Cp style=\"display: none;\">\u003Cmp-style-type data-value=\"3\">\u003C/mp-style-type>\u003C/p>\u003C/div>",[257,266,274,282,290,298,306,314],{"id":258,"title_md5":259,"publish_date":260,"author_md5":261,"is_original":23,"collection":262,"summary_md5":263,"cover_url":264,"cover_url_1_1":265},207,"7a39aaf30ce3a56e97eff69e83d8773e","2024-08-01","bc27fa490c4d0d525bac812fc0793534","#Buffett","f2fe71f1fe3b22d3e284a0c3b475f7fd","article_res/cover/1aa0c688a3c0c88bdbe206fef021d450.jpeg","article_res/cover/22e9be4de3802e882c2d274130d477d5.jpeg",{"id":267,"title_md5":268,"publish_date":269,"author_md5":261,"is_original":4,"collection":270,"summary_md5":271,"cover_url":272,"cover_url_1_1":273},472,"f99c6499f28b0092d5cf9c7604df7b67","2023-04-22","#LLM #Langchain","f789bbe69e94d520a5880133aa215c28","article_res/cover/57a4c44db61509438f738c29ee5eaa37.jpeg","article_res/cover/0704cb289d70636c7d54e91427ffb0d8.jpeg",{"id":275,"title_md5":276,"publish_date":277,"author_md5":278,"is_original":4,"collection":5,"summary_md5":279,"cover_url":280,"cover_url_1_1":281},527,"0aa029227a1a451cc0943dfb7cf186e7","2022-05-29","e51e79c6d37e0651249b385b645d3af0","2d0a315d9655007eb97263e15ea5513e","article_res/cover/e4322b6d5fbb814c40b7a0da5b6c7e48.jpeg","article_res/cover/e6b94112ce60606280e1f80c7b22dcd2.jpeg",{"id":283,"title_md5":284,"publish_date":285,"author_md5":261,"is_original":23,"collection":286,"summary_md5":287,"cover_url":288,"cover_url_1_1":289},172,"3daaea69691e09c5f8af7df545501d11","2024-09-20","#AI 3D Generator","c6eed6b9a6da6ba50ed82f65ac6455da","article_res/cover/bdebefa89e9ad647cade3cefe41d9e43.jpeg","article_res/cover/0525bd5f2d8b4587bbc98fe43e783af3.jpeg",{"id":291,"title_md5":292,"publish_date":293,"author_md5":294,"is_original":4,"collection":5,"summary_md5":295,"cover_url":296,"cover_url_1_1":297},557,"4faa16c9ff4d87d59c3378a2a3e3a6cb","2022-04-29","8b3607d0f4181a3cb6ffdccf7185f09b","c58f6a7c526c526ce0bfda938cdc8eb1","article_res/cover/7a9b1375ed9bb298154981bae42b794d.jpeg","article_res/cover/afa281dd52bc0454e6735daa8e6b0706.jpeg",{"id":299,"title_md5":300,"publish_date":301,"author_md5":261,"is_original":23,"collection":302,"summary_md5":303,"cover_url":304,"cover_url_1_1":305},344,"0289cf171a6a5f3197a4a658b18d084b","2024-01-12","#Object Detection #AI Image Generator #LLM","4683a37b0baacdcdb1119c25f45ce520","article_res/cover/5de43be205fd639aa478da130187b2a6.jpeg","article_res/cover/c95bdda03e7b7643d4f3fafa1387bfa2.jpeg",{"id":307,"title_md5":308,"publish_date":309,"author_md5":261,"is_original":23,"collection":310,"summary_md5":311,"cover_url":312,"cover_url_1_1":313},295,"2cb0f604447fcbb1b67c78636d3372d0","2024-04-23","#Meta","2a99d025754cf0acc4a25ea78d52d94f","article_res/cover/cd837191a7a4ad93501eb5ca02c920ce.jpeg","article_res/cover/f1980ea03a5d68f697f9c5d43d5e60fb.jpeg",{"id":315,"title_md5":316,"publish_date":317,"author_md5":261,"is_original":4,"collection":5,"summary_md5":318,"cover_url":319,"cover_url_1_1":320},281,"78924dd1c3a61f681af22c31a86f50ba","2024-05-07","d7b3cd27e51b0af7596a1b29d74b1c91","article_res/cover/0f8da868f4e3f79e161015bc1081495a.jpeg","article_res/cover/caf9d41c441808baadef7616cc3816fc.jpeg",{"related":322,"small":362},[323,331,339,347,354],{"id":324,"publish_date":325,"is_original":23,"collection":326,"cover_url":327,"cover_url_1_1":328,"title":329,"summary":330,"author":28},466,"2023-05-06","#LLM","article_res/cover/aac8df76a76b1290258d2661a57ce8c0.jpeg","article_res/cover/ce25a2edb9fbec73f6af894d85173982.jpeg","LangChain Reads PDFs (Part I)","Artificial intelligence is not a separate entity from us, but a reflection of our own mind. \n-《Impromptu》",{"id":332,"publish_date":333,"is_original":4,"collection":334,"cover_url":335,"cover_url_1_1":336,"title":337,"summary":338,"author":28},263,"2024-05-27","#Google #Gemini","article_res/cover/4b5d38ebfb1d0471baf24153d8358418.jpeg","article_res/cover/703059fe715f16da848efe47aa1a34bb.jpeg","Google Workspace + Gemini","Bring your best ideas to life with Gemini for Google Workspace",{"id":340,"publish_date":341,"is_original":23,"collection":342,"cover_url":343,"cover_url_1_1":344,"title":345,"summary":346,"author":28},272,"2024-05-18","#AI Avatar","article_res/cover/9820666229716f76781eb3ec035bc90e.jpeg","article_res/cover/dabaa35458f0c8f35d6df114336f0091.jpeg","【New Features in Synthesia】Expressive Virtual Humans and Voice Cloning","AI Avatar can deliver their scripts like real actors, with the appropriate tone of voice, body language, and lip-syncing",{"id":348,"publish_date":349,"is_original":4,"collection":5,"cover_url":350,"cover_url_1_1":351,"title":352,"summary":353,"author":28},334,"2024-01-27","article_res/cover/559efa3a43c7fa1bcea1482e79158733.jpeg","article_res/cover/34e9689d58317acfe4660373d1e41c13.jpeg","DePIN in \"CRYPTO THESES 2024\"","I don’t think there is a more important area of long-term development than DePIN.",{"id":355,"publish_date":356,"is_original":4,"collection":5,"cover_url":357,"cover_url_1_1":358,"title":359,"summary":360,"author":361},606,"2022-03-11","article_res/cover/0c511c5b29ba194b2ac045116d982724.jpeg","article_res/cover/5ef367446a709f88314204585ffe6e40.jpeg","How to read financial statements - Balance Sheet","We will reject interesting opportunities rather than over-leverage our balance sheet. ​- Warren Buffett","Course notes",[363,369,375],{"title":10,"list":364},[365,366,367,368],{"id":96,"publish_date":97,"is_original":23,"collection":98,"cover_url":99,"cover_url_1_1":100,"title":101,"summary":102,"author":28},{"id":104,"publish_date":105,"is_original":23,"collection":106,"cover_url":107,"cover_url_1_1":108,"title":109,"summary":110,"author":28},{"id":112,"publish_date":113,"is_original":23,"collection":114,"cover_url":115,"cover_url_1_1":116,"title":117,"summary":118,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"title":222,"list":370},[371,372,373,374],{"id":120,"publish_date":113,"is_original":23,"collection":121,"cover_url":122,"cover_url_1_1":123,"title":124,"summary":125,"author":28},{"id":166,"publish_date":167,"is_original":23,"collection":168,"cover_url":169,"cover_url_1_1":170,"title":171,"summary":172,"author":28},{"id":227,"publish_date":228,"is_original":23,"collection":229,"cover_url":230,"cover_url_1_1":231,"title":232,"summary":233,"author":28},{"id":235,"publish_date":236,"is_original":23,"collection":73,"cover_url":237,"cover_url_1_1":238,"title":239,"summary":240,"author":28},{"title":242,"list":376},[],[8,9,10],[8,12,13,14,9,10,15,16,17,18],["Reactive",245],1754646414627]